臺灣博碩士論文加值系統

六標準差研究建議公司為符合顧客要求而不斷進行品質改善。但是，六標準差專案的重要目標是減少品質成本進而獲得利潤。許多公司為增加產能與利潤進行品質持續改善。六標準差手法是對品質改善朝向六標準製程無變異的有效工具。但是，組織應考慮完成六標準差專案可能投入成本及重要性,專案經理或主管對於了解六標準差目的及設定最佳的改善門檻絶非易事。現在，我們試著發展一套多目標規劃模型，以評估六標準差專案決策，協助主管與專案領導人評估製程改善機會。此多目標規劃模型可計算製程標準差水準，並考慮液晶顯示器多段製程生產良率。並考量其他因子: 例如投資成本、利潤及期望標準差水準…等等。
研究結果顯示，多目標規劃模型能夠同時計算出最佳的六標準差水準及組織利潤。我們可以決定繼續或終止六標準差專案，當此專案符合顧客所要求的最佳品質而進行策略性的考量。當組織欲決定最佳製程的選擇時，必須考量到許多的限制條件，例如最小投資成本、改善預算、最大標準差水準及最佳製程能力…等等。多目標規劃可得最佳解, 而藉六標準差水準決策模式能夠有效的幫助主管決定六標準差專案是否值得推行。

Researchers of Six Sigma have often suggested that the quality improvement activities are continuous in order to meet customer satisfaction or requirement. Another important objective of a six sigma project was to gain the profit result from the decreased Cost of poor quality (COPQ) after improvement has been done. The most of enterprises were carrying out quality continuous improvement in order to increase productivity and profit margin. Six sigma was an effective tool to improve quality and ultimately the goal of Six Sigma is to move toward no variation in process. However, considering the extra investment that may be made in a six sigma project, it is important to identify the profit that is brought to the organizations. On the other hand, it wasn’t easily for a project leader or manager to understand the purpose and to set a threshold to decide when the improving was optimal. Now, we try to develop a model to evaluate the six sigma project decision making with a multi-objective programming model that will assist manager and project leader to decide process improving opportunities. It is a multi-objective goal programming model about calculating Sigma level for a typical Thin Film Transistor (TFT) process. The model considers a multi-stage process rolled throughput yield in a TFT Liquid Crystal Display (LCD) major Array, Cell and Module process. Meanwhile, the other factors such as investment cost, profit …and expected sigma level will be also taken in consideration in this model.
Result of this study showed a multi-objectives goal programming model can calculate the optimal six sigma level for performing process alternative and the organization can reap the profit from it at the same time. We can determine to continue or to terminate the six sigma project to meet optimal quality from VOC with strategic consideration. When the organizations want to decide the optimal process alternatives, the organizations need to consider many constraints such as minimum cost investment, improvement budget, maximum sigma level and optimal process capability…etc. The multi-objective problems can be solved in this model with optimal solution! Optimal Sigma level decision making model can effectively help manager to decide whether to continue the six sigma project.

List of Contents
List of Contents VI
List of Tables VIII
List of Figures IX
Notation XI
Chapter 1 Introduction - 1 -
1.1 Background and Motivation - 1 -
1.2 Problem definition - 4 -
1.3 Research Objectives - 8 -
1.4 Multi-Objectives of the model: - 9 -
1.5 Thesis Framework - 9 -
1.6 Research Limitation - 11 -
Chapter 2 Literature Review - 12 -
2.1 On the optimal selection of process alternatives - 12 -
2.2 Six Sigma Level - 13 -
2.3 Multi-criteria Decision Making - 16 -
2.4 Cost of Quality(COQ) - 23 -
Chapter 3 Model Development - 27 -
3.1 Problem Description - 27 -
3.2 Assumption and limitation - 28 -
3.3 Constraints explain - 28 -
3.4 Model Development - 29 -
Chapter 4 Case Study - 33 -
4.1 TFT LCD Manufacturing Process - 33 -
4.2 Rolled Throughput Yield - 34 -
Chapter 5 Summary and Further Research - 40 -
5.1 Results of typical LCD process RTY=A x C x M: - 40 -
5.2 Summary & Discussion - 46 -
5.3 Future Research - 48 -
Reference - 50 -
Appendix A: Monitor, Notebook PC Panel Price Trend - 53 -
Appendix B : Sigma Level Comparison - 54 -
Appendix C : Lingo Program - 56 -

1. Kumar, U. Dinesh; Nowicki, David; Ramírez-Márquez, José Emmanuel; et. al. On the optimal selection of process alternatives in a Six Sigma implementation International Journal of Production Economics Volume: 111, Issue: 2, February, 2008, pp. 456-467
2. Chen, K.S.; Wang, C.H.; Chen, H.T., A MAIC approach to TFT-LCD panel quality improvement Microelectronics Reliability Volume: 46, Issue: 7, July, 2006, pp. 1189-1198
3. Donald P. Lynch, What is six sigma? University of Michigan Center for Professional Development.
4. Spencer Graves (1998) “Statistical Quality Control of a Multi-Step Production Process using Total Process Yield”, Quality Engineering, 11(2), pp. 187-195 (2001) “Six Sigma Rolled Throughput Yield” Quality Engineering, 14(2) (forthcoming)
5. M. Schneiderman, Optimum Quality Costs and Zero Defects: Are They Contradictory Concepts? Quality Progress, November 1986
6. Ching-Ter Chang *, A modified goal programming model for piecewise linear functions, 2002 Elsevier Science B.V., May 2001
7. Bernard W. Multicriteria Decision Making, Taylor III Introduction to Management Science 9th ed. P355-P388 2007.
8. Kalyanmoy Deb. Non-linear Goal Programming using Multi-Objective Genetic Algorithms. Technical Report CI-60/98, University of Dortmund, Germany, 1999.
9. Nonlinear goal programming models quantifying the bullwhip effect in supply chain based on ARIMA parameters. Elsevier, Amsterdam, PAYS-BAS (1977) (Revue)
10. Kun-Lin Hsieh a,*, Yen-Sheng Lu b,1 Model construction and parameter effect for TFT-LCD process based on yield analysis by using ANNs and stepwise regression. Expert Systems With Applications Volume: 34, Issue: 1, January, 2008, pp. 717-724
11. Kalyanmoy Deb. Non-linear Goal Programming using Multi-Objective Genetic Algorithms. Technical Report CI-60/98, University of Dortmund, Germany, 1999.
12. Joly, M.; Pinto, J.M. Mixed-integer programming techniques for the scheduling of fuel oil and asphalt production Chemical Engineering Research and Design Volume: 81, Issue: 4, April, 2003, pp. 427-447
13. Hong Mo Yang, Byung Seok Choi, Hyung Jin Park, Min Soo Suh, Bongsug (Kevin) Chae Supply chain management six sigma: a management innovation methodology at the Samsung Group
14. F. Zhang and W. B. Roush1, 2002, Multiple-Objective (Goal) Programming Model for Feed Formulation:An Example for Reducing Nutrient Variation, Poultry Science Association,
15. Markarian, Jennifer, What is Six Sigma? Reinforced Plastics Volume: 48, Issue: 7, July - August, 2004, pp. 46-49
16. Ling Xu, Jian-Bo Yang, Introduction to Multi-Criteria Decision Making and the Evidential Reasoning Approach, Working Paper No. 0106, May 2001